Detecting road conditions based on braking event data received from vehicles

Abstract

Data is received regarding vehicle braking events, each event occurring on one of a plurality of vehicles, and each event associated with a location. A determination is made that the braking events correspond to a pattern. Based on determining that the braking events correspond to the pattern, a first location is identified. In response to identifying the first location, at least one action is performed.

What is claimed is: 
     
         1 . An apparatus comprising:
 at least one processor; and   memory storing instructions configured to instruct the at least one processor to:
 determine that an artificial neural network (ANN) of a vehicle is failing to properly operate; and 
 in response to determining that the ANN is failing to properly operate, cause a change to the vehicle. 
   
     
     
         2 . The apparatus of  claim 1 , wherein determining that the ANN is failing to properly operate comprises determining that the ANN is failing to identify at least one object. 
     
     
         3 . The apparatus of  claim 1 , wherein the instructions are further configured to instruct the processor to:
 receive first data from the vehicle; and   receive second data from other vehicles;   wherein determining that the ANN is failing to properly operate comprises comparing the first data and second data.   
     
     
         4 . The apparatus of  claim 3 , wherein the instructions are further configured to instruct the processor to train the ANN using at least one of the first data or the second data. 
     
     
         5 . The apparatus of  claim 3 , wherein the second data comprises a plurality of objects and corresponding locations. 
     
     
         6 . The apparatus of  claim 1 , wherein the change to the vehicle is at least one of updating data used by the ANN, or training the ANN using new data. 
     
     
         7 . The apparatus of  claim 1 , wherein the ANN provides an output from analyzing image data collected by the vehicle, and determining that the ANN is failing to properly operate comprises comparing the output to a map of object locations. 
     
     
         8 . The apparatus of  claim 7 , wherein the instructions are further configured to instruct the processor to use the map to provide a navigation service to the vehicle. 
     
     
         9 . An apparatus comprising:
 at least one processor; and   memory storing instructions configured to instruct the at least one processor to:
 receive first data from a vehicle; 
 evaluate the first data; 
 generate, in response to the evaluation, an updated artificial neural network (ANN); and 
 load the updated ANN into the vehicle. 
   
     
     
         10 . The apparatus of  claim 9 , wherein the first data is received by a server, the first data is an identification of an object, and evaluating the first data comprises determining whether the identification corresponds to object data stored by the server. 
     
     
         11 . The apparatus of  claim 9 , wherein the first data is sensor data collected by at least one sensor of the vehicle. 
     
     
         12 . The apparatus of  claim 9 , wherein the updated ANN is configured to provide an output used to control steering or braking of the vehicle. 
     
     
         13 . The apparatus of  claim 12 , wherein at least one input to the updated ANN comprises data collected by at least one sensor of the vehicle. 
     
     
         14 . An apparatus comprising:
 at least one processor; and   memory storing instructions configured to instruct the at least one processor to:
 receive first data from sensors of a plurality of vehicles; 
 evaluate, using the first data, an artificial neural network (ANN) of a vehicle; and 
 in response to the evaluation, cause an action by the vehicle. 
   
     
     
         15 . The apparatus of  claim 14 , wherein the instructions are further configured to instruct the processor to store a map based on the first data. 
     
     
         16 . The apparatus of  claim 15 , wherein the evaluation comprises comparing an output of the ANN to the map. 
     
     
         17 . The apparatus of  claim 14 , wherein the action is updating of firmware of the vehicle. 
     
     
         18 . The apparatus of  claim 14 , wherein the action is terminating an autonomous navigation mode of the vehicle. 
     
     
         19 . The apparatus of  claim 14 , wherein the ANN is a first ANN, and evaluating the first ANN is based on an output from a second ANN of a server that uses the first data as input. 
     
     
         20 . The apparatus of  claim 14 , wherein the instructions are further configured to instruct the processor to send the first data to the vehicle, and cause the vehicle to train the ANN using the first data.